INDEX

Explanations

references to personal ownership and possession

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

cret

-0.16

icer

-0.14

imest

-0.14

enthal

-0.14

isting

-0.13

 boundary

-0.13

ksi

-0.13

Exc

-0.13

POSITIVE LOGITS

 amalg

0.15

<TResult

0.15

DBC

0.14

inet

0.14

.spin

0.14

çĽ

0.14

_UNS

0.14

-Cs

0.14

êµĲ

0.14

ays

0.13

Activations Density 0.026%

references to personal ownership and possession

No Known Activations