INDEX

Explanations

references to ceiling or related architectural elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

ette

-0.18

maze

-0.16

ya

-0.15

lig

-0.15

errer

-0.15

-0.14

xe

-0.14

rou

-0.14

mann

-0.14

orsche

-0.14

POSITIVE LOGITS

YLON

0.19

asar

0.18

asing

0.17

ILING

0.17

idla

0.17

-ce

0.17

iag

0.16

vier

0.16

ylon

0.16

Ce

0.15

Activations Density 0.019%

references to ceiling or related architectural elements

No Comments

No Known Activations