INDEX

Explanations

names of people and locations

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

addtogroup

-0.15

inois

-0.13

hir

-0.13

Qed

-0.13

imon

-0.13

roys

-0.12

à¤¦à¤°

-0.12

ÐµÑĤÐµÑĢÐ±

-0.12

elas

-0.12

Ð»Ð¸ÑĪÐºÐ¾Ð¼

-0.12

POSITIVE LOGITS

á¿¦

0.15

thumbnail

0.14

tridge

0.14

 Sudoku

0.14

/gin

0.14

 rencont

0.13

orizontal

0.13

Wel

0.13

umba

0.13

rame

0.13

Activations Density 0.381%

names of people and locations

No Comments

No Known Activations