INDEX

Explanations

statements indicating actions or opinions expressed by individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

ignum

-0.16

Ð²Ð¸ÑĤ

-0.14

illy

-0.14

awe

-0.14

anz

-0.13

irsch

-0.13

ignKey

-0.13

ins

-0.13

orrh

-0.13

_TER

-0.13

POSITIVE LOGITS

roke

0.15

Zot

0.15

Äįin

0.14

 vign

0.14

inx

0.14

zilla

0.14

rador

0.14

ROKE

0.13

alar

0.13

Activations Density 0.089%

statements indicating actions or opinions expressed by individuals

No Comments

No Known Activations