INDEX

Explanations

locations and spatial references in a text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

enton

-0.17

RL

-0.15

erson

-0.15

roupon

-0.15

oser

-0.14

unker

-0.14

RYPTO

-0.14

ÛĮØ´ÙĨ

-0.14

rong

-0.14

ronic

-0.14

POSITIVE LOGITS

_inner

0.17

ikel

0.16

nett

0.16

anmar

0.16

 Himal

0.14

entin

0.14

 ç³

0.14

ermann

0.14

 river

0.14

 desert

0.14

Activations Density 0.005%

locations and spatial references in a text

No Comments

No Known Activations