INDEX

Explanations

punctuation, symbols, and words that indicate value or quantity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

atura

-0.16

pute

-0.15

Bik

-0.15

viso

-0.15

 Verm

-0.14

á»Ĩ

-0.14

Ã´i

-0.14

iox

-0.14

cheon

-0.14

elyn

-0.13

POSITIVE LOGITS

0.17

0.15

.tmp

0.15

ErrMsg

0.15

isson

0.14

dept

0.14

.tap

0.14

Activations Density 0.001%

punctuation, symbols, and words that indicate value or quantity

No Comments

No Known Activations