INDEX

Explanations

phrases involving the word "to" indicating intention or purpose

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

 Singer

-0.15

uja

-0.15

ogl

-0.15

oretical

-0.14

ÙĪØ¬

-0.13

GAS

-0.13

afc

-0.13

 Claus

-0.13

acha

-0.13

atas

-0.13

POSITIVE LOGITS

_MAKE

0.14

èĩº

0.14

 States

0.14

elden

0.14

sol

0.14

ixon

0.14

patial

0.14

Ø§Ø¦Ùĩ

0.13

 Homo

0.13

ilet

0.13

Activations Density 0.396%

phrases involving the word "to" indicating intention or purpose

No Comments

No Known Activations