INDEX

Explanations

phrases indicating contrast or exceptions

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

eton

-0.18

spath

-0.16

otti

-0.15

jam

-0.15

undle

-0.15

berger

-0.15

.Api

-0.14

ãģ¤ãģ¶

-0.14

onden

-0.14

sov

-0.14

POSITIVE LOGITS

auga

0.17

CHAIN

0.17

sz

0.15

ainers

0.14

Neh

0.14

cid

0.14

 Chan

0.13

 Skinner

0.13

ls

0.13

atan

0.13

Activations Density 0.117%

phrases indicating contrast or exceptions

No Comments

No Known Activations