INDEX

Explanations

references to specific geographical locations and quantifiers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

quelle

-0.14

ones

-0.14

 ones

-0.14

udi

-0.13

_beg

-0.13

ota

-0.13

yang

-0.13

 fronts

-0.12

POSITIVE LOGITS

 upcoming

0.19

 forthcoming

0.18

 current

0.18

 reason

0.18

 mere

0.18

 there

0.17

 existing

0.16

å¼ķãģį

0.15

 proposed

0.15

 decision

0.15

Activations Density 0.283%

references to specific geographical locations and quantifiers

No Comments

No Known Activations