INDEX

Explanations

concepts related to challenges and assessments in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ÂŃi

-0.18

upo

-0.17

iyan

-0.15

istics

-0.15

GetWidth

-0.15

anko

-0.15

onga

-0.14

setw

-0.14

aska

-0.14

AVED

-0.14

POSITIVE LOGITS

 song

0.17

 Song

0.16

ly

0.14

olini

0.14

yen

0.14

Ø§Ø²

0.14

iber

0.14

zie

0.14

ijn

0.14

wp

0.14

Activations Density 0.006%

concepts related to challenges and assessments in various contexts

No Comments

No Known Activations