INDEX

Explanations

the phrase "next" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

-0.16

heck

-0.15

ëª°

-0.15

beck

-0.15

-0.14

rans

-0.14

tw

-0.14

AccessType

-0.14

-Allow

-0.14

inz

-0.14

POSITIVE LOGITS

oller

0.17

eri

0.16

NullOr

0.15

ork

0.14

 Stuff

0.14

elerik

0.14

-door

0.14

acus

0.14

/release

0.14

 lÆ°u

0.14

Activations Density 0.021%

the phrase "next" in various contexts

No Comments

No Known Activations