INDEX

Explanations

names and proper nouns related to legal, geographical, or political contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

lÃ¡

-0.16

 Franti

-0.15

aby

-0.14

.localized

-0.14

(Have

-0.13

ovny

-0.13

ries

-0.13

ãĥĮ

-0.13

Ã³t

-0.13

undry

-0.13

POSITIVE LOGITS

ÌĨ

0.15

Ø®Øª

0.15

von

0.14

usa

0.13

ÙĪÚ¯Ø±

0.13

IC

0.12

ï»¿↵↵

0.12

.lib

0.12

USA

0.12

 Dive

0.12

Activations Density 0.206%

names and proper nouns related to legal, geographical, or political contexts

No Comments

No Known Activations