INDEX

Explanations

occurrences of the word "have" in various forms and contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

uter

-0.15

nat

-0.15

$core

-0.14

sik

-0.14

ILI

-0.14

ÑĥÐºÐ°

-0.14

iginal

-0.14

suming

-0.14

ove

-0.14

łéĻ¤

-0.14

POSITIVE LOGITS

Part

0.15

 Part

0.14

quier

0.14

estr

0.14

 sede

0.14

aar

0.14

ikki

0.13

Äįek

0.13

kÃ³w

0.13

Activations Density 0.075%

occurrences of the word "have" in various forms and contexts

No Comments

No Known Activations