INDEX

Explanations

words related to presentations and public speaking engagements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

uars

-0.15

.AutoScaleMode

-0.15

å¯©

-0.15

rowsable

-0.15

ì»¤ìĬ¤

-0.14

bÃŃr

-0.14

okin

-0.14

arf

-0.14

ocale

-0.14

shal

-0.14

POSITIVE LOGITS

 talk

0.69

 talks

0.63

 Talk

0.57

 lecture

0.56

talk

0.54

Talk

0.54

 lectures

0.51

 Talks

0.50

-talk

0.50

lecture

0.45

Activations Density 0.171%

words related to presentations and public speaking engagements

No Comments

No Known Activations