INDEX

Explanations

phrases that suggest self-centeredness or egotism

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

ainless

-0.13

ë¶

-0.13

 remot

-0.13

Ð°Ð½Ð´

-0.13

 existence

-0.13

edor

-0.13

ilog

-0.13

defgroup

-0.13

universal

-0.12

eof

-0.12

POSITIVE LOGITS

 activity

0.16

onor

0.15

 possibilities

0.15

osu

0.15

pent

0.15

yen

0.15

 symbolism

0.15

 surprises

0.14

 Activity

0.14

ContentView

0.14

Activations Density 0.049%

phrases that suggest self-centeredness or egotism

No Comments

No Known Activations