INDEX

Explanations

occurrences of the term "android" and associated layout attributes

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

dcc

-0.16

lessness

-0.15

leur

-0.15

ting

-0.14

atoi

-0.14

anic

-0.14

ãĤĪãĤĬ

-0.14

½æķ°

-0.14

ideographic

-0.14

reated

-0.14

POSITIVE LOGITS

amat

0.15

ector

0.15

ucks

0.15

¦

0.15

/System

0.14

 Prairie

0.14

quist

0.14

zn

0.13

uction

0.13

Gap

0.13

Activations Density 0.003%

occurrences of the term "android" and associated layout attributes

No Comments

No Known Activations