INDEX

Explanations

references to geographical features or locations, particularly related to banks or shores

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

ç½

-0.15

raith

-0.15

/xhtml

-0.14

olulu

-0.14

Ð¾ÐºÐ°Ð·

-0.14

erset

-0.14

chas

-0.14

ĶåĽŀ

-0.14

 cáº§m

-0.14

 TRACE

-0.14

POSITIVE LOGITS

aupt

0.16

omi

0.15

emet

0.14

structures

0.14

rypton

0.14

uron

0.14

 intern

0.14

 strr

0.14

table

0.14

ilir

0.14

Activations Density 0.058%

references to geographical features or locations, particularly related to banks or shores

No Comments

No Known Activations