INDEX

Explanations

instances of the word "published" along with related terms indicating publication details

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

akens

-0.16

leo

-0.15

dk

-0.15

oth

-0.15

 Pale

-0.14

 cáº§u

-0.14

ãģĵãĤį

-0.14

_gettime

-0.14

arine

-0.14

igli

-0.14

POSITIVE LOGITS

 Rico

0.16

ÑĢÐ°ÑģÑĤÐ°

0.14

azer

0.14

rias

0.14

ç

0.14

eken

0.14

unist

0.13

.UnitTesting

0.13

 Pressure

0.13

isu

0.13

Activations Density 0.007%

instances of the word "published" along with related terms indicating publication details

No Comments

No Known Activations