INDEX

Explanations

URLs or web links 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 @ 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ouv

-0.16

 $('#'

-0.15

Ã¡t

-0.15

pras

-0.15

pect

-0.15

 Guil

-0.15

raman

-0.15

-0.14

erson

-0.14

 Davidson

-0.14

POSITIVE LOGITS

istrovstvÃŃ

0.15

\Php

0.15

/TR

0.14

ÑĢÐ°ÑħÐ¾Ð²

0.14

amarin

0.14

iali

0.14

dain

0.14

ImageContext

0.14

TRS

0.13

Uvs

0.13

Activations Density 0.008%

URLs or web links in the text

No Comments

No Known Activations