INDEX

Explanations

instances of the word "announced" and its variations 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 @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

olls

-0.16

rale

-0.15

iggins

-0.15

cu

-0.15

mes

-0.14

ides

-0.14

().'/

-0.14

aps

-0.14

hek

-0.14

ÑĩÐ°

-0.14

POSITIVE LOGITS

edly

0.20

ment

0.18

 plans

0.18

(strict

0.18

aged

0.16

laz

0.16

asca

0.15

eg

0.15

ounced

0.15

Activations Density 0.020%

instances of the word "announced" and its variations in various contexts

No Comments

No Known Activations