INDEX

Explanations

a wide range of nouns and relevant phrases connected to specific categories or contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

-0.15

anagan

-0.15

ç·Ĵ

-0.14

iqueta

-0.14

 afflict

-0.14

Ã¼z

-0.14

 velit

-0.14

.games

-0.14

quette

-0.13

POSITIVE LOGITS

Ð¾Ñħ

0.18

hang

0.18

eness

0.14

stoff

0.14

ovich

0.13

æľį

0.13

Jou

0.13

Zem

0.13

hores

0.13

piring

0.13

Activations Density 0.036%

a wide range of nouns and relevant phrases connected to specific categories or contexts

No Comments

No Known Activations