INDEX

Explanations

instances of the word "related" and its variations, indicating associations or connections

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

ISTIC

-0.18

iran

-0.17

ÙĬØ§Øª

-0.16

ibName

-0.15

lio

-0.15

isci

-0.15

rav

-0.14

ÐµÑĢÑĤÐ°

-0.14

vrier

-0.14

rego

-0.14

POSITIVE LOGITS

ness

0.21

inos

0.16

neas

0.16

iability

0.14

.getRoot

0.14

 cool

0.14

raÃ§

0.14

bis

0.14

PLATFORM

0.14

æ³Ĭ

0.13

Activations Density 0.019%

instances of the word "related" and its variations, indicating associations or connections

No Comments

No Known Activations