INDEX

Explanations

textual instructions or descriptions of processes and steps

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

uid

-0.19

acz

-0.16

Gos

-0.15

.InnerException

-0.14

Ä±lÄ±m

-0.14

eral

-0.14

jit

-0.14

ÑĢÐ¾ÑģÑĤÐ¾

-0.14

ache

-0.14

ault

-0.13

POSITIVE LOGITS

anker

0.18

:↵

0.16

0.15

:↵↵

0.15

 Andersen

0.15

mailer

0.14

swer

0.14

ssize

0.14

rema

0.14

:č↵

0.13

Activations Density 0.062%

textual instructions or descriptions of processes and steps

No Comments

No Known Activations