INDEX

Explanations

references to destruction and debris

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

-0.16

dea

-0.15

serter

-0.14

dio

-0.13

_SUBJECT

-0.13

 perd

-0.13

elight

-0.13

POSITIVE LOGITS

 debris

0.39

 wreckage

0.39

 rubble

0.36

 remains

0.33

 wreck

0.31

 ruins

0.31

 char

0.29

 fragments

0.26

 ruin

0.26

 ruined

0.25

Activations Density 0.125%

references to destruction and debris

No Comments

No Known Activations