INDEX

Explanations

sequences of numbers and symbols, likely related to citations or references in academic texts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

 Christoph

-0.17

usk

-0.15

ssf

-0.14

 Patch

-0.14

-src

-0.14

awi

-0.13

 Airways

-0.13

ayÄ±p

-0.13

ħ§

-0.13

udiant

-0.13

POSITIVE LOGITS

htable

0.17

 successor

0.16

 ÑģÑĤÐ¾ÑĢ

0.16

lopedia

0.15

rollo

0.15

htags

0.15

raya

0.15

Ñĺ

0.15

ROTO

0.14

IPA

0.14

Activations Density 0.014%

sequences of numbers and symbols, likely related to citations or references in academic texts

No Comments

No Known Activations