INDEX

Explanations

instances of parentheses and other punctuation, often indicating cited sources or references in a text

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

aged

-0.15

Ryu

-0.14

coil

-0.14

letters

-0.14

cala

-0.13

Łèĥ½

-0.13

Ã¡b

-0.13

_GP

-0.13

story

-0.13

abis

-0.13

POSITIVE LOGITS

 indem

0.18

 Ying

0.16

 Trang

0.15

ãĥŃãĥ¼

0.14

anke

0.14

rop

0.14

 Saved

0.14

inceton

0.14

ovol

0.14

azzi

0.13

Activations Density 0.007%

instances of parentheses and other punctuation, often indicating cited sources or references in a text

No Comments

No Known Activations