INDEX

Explanations

place names and geographic locations

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

ocode

-0.15

æĮ¯ãĤĬ

-0.15

esome

-0.15

/code

-0.14

oad

-0.14

_INCREF

-0.14

IVEN

-0.14

flip

-0.14

 flip

-0.14

antha

-0.13

POSITIVE LOGITS

ÑĢÐ°Ñĩ

0.15

isse

0.15

uye

0.15

uis

0.14

orz

0.14

quarters

0.14

dsl

0.14

 æĪĲ

0.14

á»ĥn

0.14

èª

0.14

Activations Density 0.109%

place names and geographic locations

No Comments

No Known Activations