INDEX

Explanations

occurrences of the word "author" and references to authors in the text

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

ismet

-0.15

intl

-0.15

mys

-0.15

 stick

-0.15

illow

-0.14

 Cove

-0.14

 skeleton

-0.14

is

-0.14

bie

-0.13

bate

-0.13

POSITIVE LOGITS

//{{

0.17

ÑıÑĩ

0.15

olio

0.15

ollah

0.15

ocaly

0.14

abilities

0.14

#ad

0.14

à¸łà¸²à¸ŀ

0.14

_userdata

0.14

Activations Density 0.003%

occurrences of the word "author" and references to authors in the text

No Comments

No Known Activations