INDEX

Explanations

references to small yet impactful actions or moments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

uzzi

-0.15

obar

-0.15

oci

-0.15

ierz

-0.14

 double

-0.14

ASURE

-0.14

sp

-0.14

_specific

-0.14

Fur

-0.14

ide

-0.14

POSITIVE LOGITS

usk

0.17

ãģĵãĤį

0.16

uster

0.16

Ã§

0.16

éłĥ

0.16

 simple

0.16

/simple

0.15

 èı²

0.15

acz

0.15

ayed

0.14

Activations Density 0.162%

references to small yet impactful actions or moments

No Comments

No Known Activations