INDEX

Explanations

references to navigation or transitions between content sections

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

career

-0.16

ansson

-0.16

vej

-0.16

nf

-0.15

elles

-0.14

.OR

-0.14

ritz

-0.14

ãģ¾ãģ¨

-0.14

ilerek

-0.14

ÄĽj

-0.14

POSITIVE LOGITS

 Aura

0.15

Fu

0.14

 Album

0.14

PSD

0.14

å¢ĵ

0.14

 unprotected

0.13

AKER

0.13

 Colt

0.13

/internal

0.13

-/

0.13

Activations Density 0.002%

references to navigation or transitions between content sections

No Comments

No Known Activations