INDEX

Explanations

phrases related to enabling or permitting actions and opportunities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

iron

-0.14

yg

-0.14

oward

-0.14

yle

-0.14

cak

-0.13

acco

-0.13

ĥ

-0.13

THR

-0.13

IRON

-0.13

ers

-0.13

POSITIVE LOGITS

ayÄ±p

0.15

łģ

0.15

upo

0.15

boro

0.14

alytics

0.14

ÏįÎ½

0.14

Ľ°

0.14

ond

0.14

DataReader

0.14

Activations Density 0.045%

phrases related to enabling or permitting actions and opportunities

No Comments

No Known Activations