INDEX

Explanations

instances of the word "call" in various contexts, often related to calls for action or attention

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

uslim

-0.16

icha

-0.14

aylor

-0.14

owitz

-0.14

ients

-0.14

ibraltar

-0.14

afka

-0.13

idge

-0.13

Ø§Ø¯Ùĩ

-0.13

iÃ§

-0.13

POSITIVE LOGITS

dib

0.19

imit

0.16

noch

0.14

 å»

0.14

nie

0.14

istream

0.14

-animate

0.14

ow

0.14

StackNavigator

0.14

 manner

0.13

Activations Density 0.058%

instances of the word "call" in various contexts, often related to calls for action or attention

No Comments

No Known Activations