INDEX

Explanations

references to barriers 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 @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

roller

-0.16

erman

-0.15

ext

-0.15

zM

-0.14

ega

-0.14

lint

-0.14

eme

-0.13

esso

-0.13

erosis

-0.13

mn

-0.13

POSITIVE LOGITS

alama

0.21

aoke

0.15

unta

0.15

idders

0.15

itchen

0.15

.gdx

0.14

ATAR

0.14

¨

0.14

ROWSER

0.14

alom

0.14

Activations Density 0.007%

references to barriers in various contexts

No Comments

No Known Activations