INDEX

Explanations

the word "basically" 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 @ 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

locker

-0.15

lexer

-0.15

arms

-0.14

ensex

-0.14

orca

-0.14

cents

-0.14

ofilm

-0.14

áº¹p

-0.14

tera

-0.14

ether

-0.14

POSITIVE LOGITS

 ComVisible

0.16

-minded

0.15

antha

0.15

emble

0.15

pulse

0.14

 Furious

0.14

ifa

0.14

æĻ´

0.14

ITA

0.14

itas

0.14

Activations Density 0.006%

the word "basically" in various contexts

No Comments

No Known Activations