INDEX

Explanations

references to content labeled with genres or categories

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

py

-0.15

PF

-0.14

pit

-0.13

 GetLastError

-0.13

utral

-0.13

avig

-0.13

oval

-0.13

ampo

-0.13

OPY

-0.13

cco

-0.13

POSITIVE LOGITS

led

0.18

Bab

0.15

ANTA

0.15

 industry

0.14

 Pres

0.14

stÃ¤nd

0.14

ãĥ³ãĥĩ

0.14

ITES

0.14

env

0.14

ourmet

0.14

Activations Density 0.004%

references to content labeled with genres or categories

No Comments

No Known Activations