INDEX

Explanations

specific referencing words and phrases related to relationships and connections

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

orp

-0.16

Ã¦kke

-0.15

dik

-0.14

aab

-0.14

blas

-0.13

 Slack

-0.13

 protest

-0.13

Names

-0.13

isions

-0.13

scriptions

-0.13

POSITIVE LOGITS

 DevComponents

0.14

 Haley

0.14

 Ø§Ùģ

0.14

å±±å¸Ĥ

0.14

 maduras

0.14

TargetException

0.14

umat

0.14

ubat

0.14

Æ°á»£ng

0.13

Nat

0.13

Activations Density 0.015%

specific referencing words and phrases related to relationships and connections

No Comments

No Known Activations