INDEX

Explanations

references to specific countries or regions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

Jeg

-0.17

ritz

-0.15

hair

-0.15

eka

-0.15

nar

-0.15

Î¸Îµ

-0.14

elsen

-0.14

åº§

-0.14

ÏİÏģÎ±

-0.14

 Suspension

-0.14

POSITIVE LOGITS

chwitz

0.16

æĲŀ

0.15

isher

0.14

serial

0.14

ä¾

0.14

Ø¨ÙĪØ¯

0.14

 giÃ¡c

0.14

antes

0.14

uada

0.14

Activations Density 0.002%

references to specific countries or regions

No Comments

No Known Activations