INDEX

Explanations

occurrences of discussions and their associated metadata

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

isz

-0.17

cke

-0.16

utenberg

-0.16

 Trap

-0.16

Ð¾ÑĤÑĢÐµÐ±

-0.16

Narrated

-0.15

aky

-0.15

aille

-0.15

alus

-0.15

imos

-0.15

POSITIVE LOGITS

 drying

0.15

Lad

0.14

 forum

0.14

forum

0.14

inka

0.14

Ø®Ø´

0.14

åŁ

0.14

Ess

0.14

Occurred

0.14

sage

0.13

Activations Density 0.010%

occurrences of discussions and their associated metadata

No Comments

No Known Activations