INDEX

Explanations

comparisons that highlight differences

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

rys

-0.17

 deadliest

-0.14

erton

-0.14

Â¦

-0.14

aylight

-0.14

-0.13

formance

-0.13

amy

-0.13

atura

-0.13

ales

-0.13

POSITIVE LOGITS

 unlike

0.19

 Unlike

0.16

Unlike

0.15

é¤

0.15

ãĥĳãĥ³

0.14

adin

0.14

à¹īà¸²à¸Ļ

0.14

olini

0.14

[assembly

0.14

Activations Density 0.027%

comparisons that highlight differences

No Comments

No Known Activations