INDEX

Explanations

phrases that indicate proximity or closeness to an outcome or goal

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

hey

-0.15

ãĤ¿ãĥ¼

-0.15

sher

-0.15

ikan

-0.14

 Duch

-0.14

EO

-0.14

<<-

-0.13

reme

-0.13

 Jahres

-0.13

ÑģÐ°Ð¼

-0.13

POSITIVE LOGITS

 royalty

0.16

deprecated

0.15

endir

0.15

zyst

0.15

zsche

0.15

 ready

0.14

ingly

0.14

ourd

0.14

ëģ

0.14

riend

0.14

Activations Density 0.132%

phrases that indicate proximity or closeness to an outcome or goal

No Comments

No Known Activations