INDEX

Explanations

names or references associated with specific individuals, particularly those appearing frequently in the text

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

Negative Logits

rowable

-0.16

ERSION

-0.15

çµ

-0.15

Ã¼re

-0.14

 Probe

-0.14

aton

-0.14

à¤¹

-0.14

Ã©f

-0.14

èķ

-0.14

reate

-0.14

POSITIVE LOGITS

oret

0.17

atchewan

0.16

ze

0.15

iske

0.15

estro

0.15

rement

0.14

sworth

0.14

CellStyle

0.14

ester

0.14

extern

0.14

Activations Density 0.122%

names or references associated with specific individuals, particularly those appearing frequently in the text

No Known Activations