INDEX

Explanations

terms associated with proximity or closeness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

-0.17

aldi

-0.16

Ð°Ð½ÑĮ

-0.15

obia

-0.14

Dra

-0.14

pector

-0.14

Eis

-0.14

reste

-0.14

akis

-0.14

anguages

-0.13

POSITIVE LOGITS

 whopping

0.25

 excess

0.19

è¨Ī

0.16

imately

0.15

|int

0.15

è¾¾

0.15

viron

0.15

aucoup

0.15

_least

0.14

 THAN

0.14

Activations Density 0.121%

terms associated with proximity or closeness

No Comments

No Known Activations