INDEX

Explanations

occurrences of obstacles or impediments to progress

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

erd

-0.15

TECTED

-0.15

éĲĺ

-0.14

usercontent

-0.14

leh

-0.14

ãģĵãģ¨ãģ¯

-0.14

fa

-0.14

 haystack

-0.14

jom

-0.13

POSITIVE LOGITS

 path

0.47

 paths

0.31

path

0.31

è·¯å¾Ħ

0.31

-path

0.31

.path

0.30

Path

0.30

 Path

0.29

 Ð¿ÑĥÑĤÐ¸

0.29

 PATH

0.28

Activations Density 0.051%

occurrences of obstacles or impediments to progress

No Comments

No Known Activations