INDEX

Explanations

references to specific groups or entities in a political or social context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

 become

-0.20

 becomes

-0.16

isko

-0.16

æĪĲä¸º

-0.15

éĤ¦

-0.15

 undergo

-0.15

ESA

-0.15

 weren

-0.15

bec

-0.15

assis

-0.15

POSITIVE LOGITS

0.18

 Trails

0.17

 trails

0.16

æŃ£åľ¨

0.16

 Äĳang

0.16

Ã¼zel

0.15

 faces

0.15

 estÃ¡

0.14

fen

0.14

 possesses

0.14

Activations Density 0.423%

references to specific groups or entities in a political or social context

No Comments

No Known Activations