INDEX

Explanations

numeric values and identifiers related to specific details or information

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

åĩ

-0.15

ä»ķ

-0.15

stown

-0.15

arrings

-0.14

ritic

-0.14

nn

-0.14

ij

-0.14

ãĥªãĤ¹

-0.13

egra

-0.13

 overd

-0.13

POSITIVE LOGITS

/lg

0.16

Jeh

0.15

ket

0.15

esel

0.15

akens

0.14

ARB

0.14

lava

0.14

 Horm

0.14

 SetLastError

0.14

 https

0.14

Activations Density 0.041%

numeric values and identifiers related to specific details or information

No Comments

No Known Activations