INDEX

Explanations

references to comparisons and contrasts between entities or concepts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Profiles

-0.18

-0.17

 Profiles

-0.17

_sets

-0.17

Lists

-0.16

 kitchens

-0.15

 Packs

-0.15

.scenes

-0.15

 Sets

-0.15

 fleets

-0.15

POSITIVE LOGITS

ToProps

0.20

ainties

0.20

 freedoms

0.19

ictions

0.19

 constraints

0.19

asures

0.18

 liberties

0.18

ibilities

0.18

 responsibilities

0.17

 Liberties

0.17

Activations Density 0.149%

references to comparisons and contrasts between entities or concepts

No Comments

No Known Activations

references to comparisons and contrasts between entities or concepts

No Comments

No Known Activations