INDEX

Explanations

sentences that summarize overall assessments or conclusions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

uels

-0.15

arat

-0.15

/../

-0.14

iterals

-0.14

iffs

-0.14

ç³

-0.14

obili

-0.14

-NLS

-0.13

wy

-0.13

opsis

-0.13

POSITIVE LOGITS

zip

0.15

rellas

0.14

ativity

0.14

/legal

0.14

ption

0.14

udden

0.13

ETS

0.13

Crud

0.13

odian

0.13

éĹ

0.13

Activations Density 0.038%

sentences that summarize overall assessments or conclusions

No Comments

No Known Activations