INDEX

Explanations

references to programming languages and libraries, particularly related to standard functions and data structures

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

acas

-0.17

aura

-0.17

ouri

-0.15

ãģªãģĮ

-0.14

borough

-0.14

 Cory

-0.14

ogram

-0.14

eton

-0.14

.hs

-0.14

lovak

-0.14

POSITIVE LOGITS

ertia

0.16

zcze

0.15

 Marion

0.15

alue

0.14

ilis

0.14

OTTOM

0.14

ì§¸

0.14

fri

0.14

erson

0.14

uth

0.14

Activations Density 0.013%

references to programming languages and libraries, particularly related to standard functions and data structures

No Comments

No Known Activations