INDEX

Explanations

repetitions of the word "like" used as a discourse marker

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

ÑĢÐ¾Ð³

-0.17

à¤¾à¤®à¤²

-0.15

 synth

-0.14

onga

-0.14

ought

-0.14

occo

-0.14

rices

-0.14

rint

-0.14

ilogy

-0.13

ummies

-0.13

POSITIVE LOGITS

ature

0.18

Yer

0.16

atel

0.16

adir

0.15

 Plum

0.15

onde

0.15

orde

0.15

usz

0.14

azor

0.14

Fon

0.14

Activations Density 0.045%

repetitions of the word "like" used as a discourse marker

No Comments

No Known Activations