INDEX

Explanations

names, particularly those of historical or prominent figures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

 Leak

-0.17

aper

-0.16

íķŃ

-0.15

ÑĥÑĢÐ°

-0.15

ãĥ¼ãĤ

-0.15

ãĥ¨

-0.15

æ©

-0.14

 reint

-0.14

ãĥ§

-0.14

.ColumnHeader

-0.14

POSITIVE LOGITS

isses

0.17

avage

0.16

ogg

0.15

erville

0.15

itter

0.15

amp

0.15

atk

0.15

leh

0.14

altar

0.14

ritis

0.14

Activations Density 0.030%

names, particularly those of historical or prominent figures

No Comments

No Known Activations