INDEX

Explanations

elements related to familial connections and bloodlines

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

scenario

-0.15

ucken

-0.15

erset

-0.14

reta

-0.14

Ä±cÄ±

-0.14

.dylib

-0.14

ighbor

-0.14

ãĤ»ãĥ³

-0.14

ãĥ¼ãĤ¹

-0.14

Ð´Ð°Ð½

-0.14

POSITIVE LOGITS

hoff

0.18

 Richardson

0.15

 both

0.15

0.14

 strictly

0.14

 Augustine

0.14

 trop

0.13

 entirely

0.13

 Choices

0.13

arity

0.13

Activations Density 0.186%

elements related to familial connections and bloodlines

No Known Activations