INDEX

Explanations

references to educational courses or training programs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

thin

-0.17

ri

-0.16

rael

-0.15

rych

-0.15

imensional

-0.15

nom

-0.15

ter

-0.15

ron

-0.15

rice

-0.15

POSITIVE LOGITS

anut

0.17

illon

0.15

yal

0.15

IGNAL

0.15

quential

0.15

NEY

0.15

illard

0.15

ignon

0.15

bellion

0.15

UPPORTED

0.14

Activations Density 0.030%

references to educational courses or training programs

No Comments

No Known Activations