INDEX

Explanations

connections and comparisons between different elements or groups

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

/embed

-0.18

dk

-0.14

á»ĵn

-0.14

DK

-0.14

ottage

-0.14

ieres

-0.14

 neither

-0.14

DN

-0.13

PPER

-0.13

.freeze

-0.13

POSITIVE LOGITS

ancybox

0.17

tet

0.15

TemplateName

0.14

olare

0.14

 Tick

0.14

loo

0.14

 PhÃº

0.14

Ð»Ð°ÑĤÐ°

0.13

riday

0.13

ä¼ģ

0.13

Activations Density 0.187%

connections and comparisons between different elements or groups

No Comments

No Known Activations