INDEX

Explanations

terms related to enforcement, compliance, and legal consequences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

ovich

-0.16

ashi

-0.16

ici

-0.14

ÎºÎ±ÏĤ

-0.13

amburger

-0.13

 xong

-0.13

rench

-0.13

 hÃ¢l

-0.13

_HELPER

-0.13

é§

-0.13

POSITIVE LOGITS

 when

0.70

 upon

0.59

when

0.59

_when

0.51

 cuando

0.50

 quando

0.49

 Upon

0.49

khi

0.49

Upon

0.48

 after

0.47

Activations Density 0.031%

terms related to enforcement, compliance, and legal consequences

No Comments

No Known Activations