INDEX

Explanations

terms related to literature or documentation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

ÐĲÑĢÑħÑĸÐ²

-0.16

arden

-0.16

LOAT

-0.15

ourcem

-0.15

imson

-0.15

beer

-0.15

rael

-0.14

vest

-0.14

emie

-0.14

Ð¼ÐµÑĤÑĮ

-0.14

POSITIVE LOGITS

.Serialization

0.15

Printf

0.15

 Banner

0.15

Coy

0.14

 ÑĤÑı

0.14

 Counter

0.14

 Weather

0.14

 Keller

0.13

ãĥ¼ãĤ¸

0.13

-to

0.13

Activations Density 0.000%

terms related to literature or documentation

No Comments

No Known Activations