INDEX

Explanations

occurrences of the word "straight" and its variations 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 @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

sein

-0.19

atomy

-0.16

rÃ¡l

-0.16

@index

-0.15

ipur

-0.14

imeter

-0.14

kate

-0.14

Stencil

-0.14

ipeg

-0.14

ikan

-0.14

POSITIVE LOGITS

-ÑĤÐ°ÐºÐ¸

0.20

iddy

0.20

er

0.19

um

0.19

ness

0.18

ãĥ³ãĥĩ

0.17

ened

0.16

reed

0.15

ie

0.15

ening

0.14

Activations Density 0.017%

occurrences of the word "straight" and its variations in various contexts

No Comments

No Known Activations