INDEX

Explanations

references to cities and urban locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

robat

-0.16

ouns

-0.15

lings

-0.14

iola

-0.14

anuts

-0.14

outil

-0.14

=explode

-0.14

krom

-0.14

ory

-0.14

/licenses

-0.14

POSITIVE LOGITS

 Garner

0.18

 Gardner

0.16

 city

0.15

avanaugh

0.15

avel

0.15

PASS

0.14

pul

0.14

Ð»ÐµÐ¶

0.14

Ð²Ð¾ÑĢ

0.14

 cities

0.14

Activations Density 0.097%

references to cities and urban locations

No Comments

No Known Activations