INDEX

Explanations

significant nouns and concepts related to human experiences and interactions

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

ember

-0.15

 CONDITIONS

-0.15

iami

-0.15

 Conditions

-0.15

Ð¾ÑĩÐ½Ð¾Ð¹

-0.14

lingen

-0.14

WithString

-0.14

 Kraj

-0.14

jie

-0.14

ascus

-0.14

POSITIVE LOGITS

.foundation

0.18

NCY

0.15

arus

0.14

 Imperial

0.14

ooky

0.14

_mv

0.14

à¹ĳ

0.13

ĥĿ

0.13

_READONLY

0.13

_defs

0.13

Activations Density 0.022%

significant nouns and concepts related to human experiences and interactions

No Comments

No Known Activations