INDEX

Explanations

references to people or groups, particularly those involved in actions or judgments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

ston

-0.15

aran

-0.14

.Include

-0.14

arkan

-0.14

 nutshell

-0.14

ichern

-0.14

 itself

-0.13

estone

-0.13

 himself

-0.13

xit

-0.13

POSITIVE LOGITS

 otherwise

0.20

 matters

0.19

otherwise

0.17

 mattered

0.17

 might

0.16

 menstr

0.16

CKER

0.16

 matter

0.16

 Matters

0.16

 Otherwise

0.16

Activations Density 0.181%

references to people or groups, particularly those involved in actions or judgments

No Comments

No Known Activations