INDEX

Explanations

references to the global context or overall environment

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

oppel

-0.16

 propensity

-0.15

peri

-0.14

inth

-0.14

apore

-0.14

Ø§Ø¶Ø±

-0.14

Ð»Ð°ÑĢÐ°

-0.14

ierung

-0.14

 componentDid

-0.14

ikh

-0.14

POSITIVE LOGITS

ije

0.15

HOOK

0.15

kiye

0.14

gnu

0.14

\Bridge

0.14

ì±ħ

0.14

ÑĤÐ¾Ð½

0.14

iles

0.13

Ã¥n

0.13

Activations Density 0.020%

references to the global context or overall environment

No Comments

No Known Activations