INDEX

Explanations

references to corners or corner-related concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

loh

-0.16

ëł¨

-0.16

Ø·ÙĬ

-0.15

ensa

-0.15

OLT

-0.15

ìĿ´ë²Ħ

-0.14

 dress

-0.14

ummer

-0.14

tle

-0.14

jour

-0.14

POSITIVE LOGITS

stones

0.24

0.19

-corner

0.19

stone

0.18

 corner

0.16

STONE

0.16

sey

0.16

erd

0.16

ste

0.16

azzi

0.16

Activations Density 0.020%

references to corners or corner-related concepts

No Comments

No Known Activations