INDEX

Explanations

questions that require an explanation or elaboration

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

FACT

-0.15

rier

-0.15

ipp

-0.15

ÏĢÎ¿ÏĦÎµ

-0.15

ullan

-0.14

inputEmail

-0.14

irth

-0.14

irst

-0.14

arkan

-0.14

ingo

-0.14

POSITIVE LOGITS

ilen

0.16

chedulers

0.14

ocale

0.14

rench

0.14

 Scheduler

0.14

TOD

0.13

contri

0.13

@qq

0.13

 sing

0.13

dil

0.13

Activations Density 0.052%

questions that require an explanation or elaboration

No Comments

No Known Activations