INDEX

Explanations

names of individuals associated with various achievements or roles

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

asaki

-0.15

 Commons

-0.14

acters

-0.14

oli

-0.14

PCP

-0.14

 Cobb

-0.13

oose

-0.13

oir

-0.13

atica

-0.13

OMB

-0.13

POSITIVE LOGITS

thon

0.16

asthan

0.15

ylon

0.14

anan

0.14

 Diss

0.14

ellungen

0.14

olars

0.13

 Bias

0.13

THON

0.13

steen

0.13

Activations Density 0.235%

names of individuals associated with various achievements or roles

No Comments

No Known Activations