INDEX

Explanations

reflexive pronouns in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

icip

-0.17

oÅ¾

-0.15

 cole

-0.15

ecute

-0.14

oes

-0.14

antu

-0.14

á»«

-0.14

_topology

-0.13

icipation

-0.13

 erle

-0.13

POSITIVE LOGITS

uls

0.22

conde

0.20

ared

0.19

ules

0.19

ãĥ³ãĥĩãĤ£

0.16

ign

0.16

 content

0.16

 Hutchinson

0.16

vez

0.15

enth

0.15

Activations Density 0.004%

reflexive pronouns in various contexts

No Comments

No Known Activations