INDEX

Explanations

legal citations and references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

ulus

-0.16

ige

-0.15

assign

-0.14

ase

-0.14

iste

-0.14

dr

-0.14

asm

-0.14

atern

-0.13

itta

-0.13

POSITIVE LOGITS

 infra

0.19

tbl

0.17

 slip

0.15

(internal

0.15

 OnTrigger

0.15

 supra

0.15

 propName

0.15

-pocket

0.14

_exports

0.14

("[

0.14

Activations Density 0.050%

legal citations and references

No Comments

No Known Activations