INDEX

Explanations

terms related to hepatitis and associated keywords

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

lim

-0.15

lij

-0.14

rt

-0.13

hood

-0.13

dbuf

-0.13

iew

-0.13

lettes

-0.13

bersome

-0.13

rad

-0.13

wheel

-0.13

POSITIVE LOGITS

stral

0.17

esda

0.15

ken

0.15

angelo

0.15

uplic

0.15

ReuseIdentifier

0.15

hton

0.15

ublish

0.15

imbledon

0.15

0.14

Activations Density 0.030%

terms related to hepatitis and associated keywords

No Comments

No Known Activations