INDEX

Explanations

occurrences of the word "on."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

.MixedReality

-0.18

AAA

-0.15

arters

-0.14

ling

-0.14

gol

-0.14

eeper

-0.14

Lint

-0.14

 golf

-0.14

hausen

-0.14

 ...(

-0.13

POSITIVE LOGITS

 Wolff

0.16

acional

0.15

logan

0.14

Specifier

0.14

ajs

0.14

 Globe

0.14

oltip

0.14

 rainy

0.14

RESH

0.14

Activations Density 0.067%

occurrences of the word "on."

No Comments

No Known Activations