INDEX

Explanations

terms related to effectiveness and implications of actions or policies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

nection

-0.16

_EXTERN

-0.16

mium

-0.16

etag

-0.16

ellas

-0.15

ulis

-0.15

utilus

-0.15

nergy

-0.15

quet

-0.15

enery

-0.15

POSITIVE LOGITS

abis

0.16

 effectively

0.16

odia

0.15

rey

0.15

urance

0.14

oud

0.13

elligent

0.13

ough

0.13

meaning

0.13

åĳ½

0.13

Activations Density 0.026%

terms related to effectiveness and implications of actions or policies

No Comments

No Known Activations