INDEX

Explanations

instances of transitional phrases that indicate additional information or elaboration

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

æŃ

-0.14

imson

-0.14

#echo

-0.13

ipt

-0.13

secs

-0.13

ainen

-0.13

PTS

-0.13

ÐµÐ¹Ð½

-0.13

-keys

-0.13

run

-0.13

POSITIVE LOGITS

izu

0.15

ths

0.15

orado

0.14

odian

0.14

acles

0.13

reator

0.13

 fact

0.13

 nowhere

0.13

owing

0.13

-being

0.13

Activations Density 0.027%

instances of transitional phrases that indicate additional information or elaboration

No Comments

No Known Activations