INDEX

Explanations

references to the English language and culture

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

iku

-0.17

bsolute

-0.17

ÐľÐŀ

-0.15

atorium

-0.14

ering

-0.14

opal

-0.14

 bigotry

-0.14

ãĤ¯ãĥĪ

-0.14

inker

-0.13

ringe

-0.13

POSITIVE LOGITS

iche

0.18

ahl

0.15

avors

0.15

anie

0.15

PURE

0.14

_gb

0.14

Ø§Ø¦

0.14

 Verde

0.14

 Virgin

0.14

Activations Density 0.059%

references to the English language and culture

No Comments

No Known Activations