INDEX

Explanations

specific proper nouns and significant terms related to organizations, locations, and fields of study

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

blr

-0.18

"nil

-0.16

ä¼ı

-0.15

ï¼ł

-0.15

WXYZ

-0.15

ERY

-0.14

atables

-0.14

$MESS

-0.14

ãĥ³ãĤ¹

-0.14

POSITIVE LOGITS

phe

0.16

 Priv

0.16

ãģĭãģ«

0.14

obus

0.14

ãģĭãĤı

0.14

 Ward

0.14

pec

0.14

apia

0.14

Af

0.14

Activations Density 0.026%

specific proper nouns and significant terms related to organizations, locations, and fields of study

No Comments

No Known Activations