INDEX

Explanations

discussions around personal identity and self-discovery

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

rous

-0.17

ista

-0.15

ze

-0.15

 rast

-0.14

 blur

-0.14

opia

-0.14

CI

-0.14

imp

-0.14

Imp

-0.14

POSITIVE LOGITS

how

0.24

 what

0.19

ãĥ¬ãĥĥãĥĪ

0.19

 cÃ³mo

0.18

How

0.17

how

0.16

ãĢģä½ķ

0.16

Ã³mo

0.16

åĵªéĩĮ

0.16

idden

0.15

Activations Density 0.179%

discussions around personal identity and self-discovery

No Comments

No Known Activations